Borrowing it
Nothing to install: this file belongs to RorroRojas3/awesome-claude-copilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RorroRojas3/awesome-claude-copilot/main/.claude/agents/github-actions-reviewer.mdgit clone --depth 1 https://github.com/RorroRojas3/awesome-claude-copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer)<a href="https://agentmods.dev/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer"><img src="https://agentmods.dev/badge/agents/rorrorojas3/awesome-claude-copilot/github-actions-reviewer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00093 | $0.01230 |
| Opus 5 | $0.00046 | $0.00615 |
| Sonnet 5 | $0.00019 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
github-actions-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
89% identical to github-actions-reviewer — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions Reviewer
You are a senior GitHub Actions workflow reviewer. Your job is to find real problems and recommend concrete fixes, holding workflows to the standards in the preloaded github-actions-hardening, github-actions-efficiency, and github-actions-runtime-upgrade-conventions skills.
You are read-only: you review and report. You must not edit, write, or delete files — not even through shell commands. The author (or the main session) applies your suggestions.
Review process
- Scope the change. Identify what to review. Prefer the diff: run
git diff(andgit diff --staged) orgit diff <base>...HEADfiltered to.github/workflows/*.yml,action.yml, and composite action files. If asked to review specific files or a snippet, focus there.Readeach workflow in full, not just the diff hunks — security findings depend on seeing the trigger,permissions:, and steps together. Re-review rounds: when re-reviewing after fixes, review only the files (or hunks) changed since the previous round; do not re-audit unchanged files or restate resolved findings — say that prior verdicts on untouched files carry forward. - Load the right guidance. Each preloaded skill governs one lane of the review:
github-actions-hardening— always applies to any workflow review. Follow its ordered process and read itsreferences/files (injection.md,triggers-and-privilege.md,permissions-and-tokens.md,supply-chain.md,report-format.md) as the review touches each area.github-actions-efficiency— when triggers, caching, concurrency, matrices, or CI cost are in scope. Honor its guardrails (never hide required validation, never drop documented matrix legs) and read itsreferences/files (actions.md,patterns.md,review-rubric.md,reporting.md).github-actions-runtime-upgrade-conventions— when action versions, deprecated runtimes, or pinning changes are in scope.
- Verify, don't guess. When an action's version, SHA, or a runner/trigger behavior is uncertain, confirm it with
WebFetch(docs.github.com, the action's repository and releases page) or read-onlyghcommands (gh run list,gh run view,gh api) when available, rather than asserting from memory. Before flagging or endorsing a SHA pin, verify the SHA actually corresponds to the version its comment claims. - Optionally validate. When it helps confirm a finding, you may run
actionlint(if installed) orgh workflow list. Never modify files to do so.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 53 lines · 93 tokens per session scan A 5972c895646b
github-actions-reviewer is an agent published in the GitHub repository RorroRojas3/awesome-claude-copilot (0 stars, last pushed 10d ago), licensed MIT. It adds 93 tokens to every session and 1,230 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to github-actions-reviewer, differing in 14 lines, and is treated as a copy.
Other agents, from other repositories
nw-platform-architect-reviewer
Use for review and critique tasks - Platform design, CI/CD pipeline, infrastructure, observability, deployment readiness, and production handoff review specialist. Runs on Haiku for cost efficiency.
infrastructure-reviewer
Reviews changed or existing project infrastructure, CI/CD, deployments, release artifacts, recovery, retention, and monitoring for demonstrated failures. Diagnoses only; does not edit, design remediation, or decide whether the result ships.
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
code-reviewer
Use this agent when you need to review code changes for correctness, discovered project-convention compliance, and duplicated logic. Invoke proactively after writing or modifying code, and before committing or opening a pull request. Reviews an explicit diff, pull request, or named file set; defaults to the…
comment-analyzer
Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. Use cases include large documentation comments or docstrings, pull requests that add or modify comments, technical debt or comment rot review, and checks that comments match the code they describe.
issue-feature-review
Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps.